Grok 4.7
Not tested yet
Language modelActive
Grok 4.7
xAI
- Released
- September 21, 2026
- Data date
- September 22, 2026
- Predecessor
- Grok 4.6
- Intelligence
- Overall score
- Price
- Input · Output / 1M tokens
- Input
- Text, Image
- Output
- Text
No published category-wide ranking is available for this model.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
CursorBench 4.0 (Show measurement, test conditions, and source)
- Source value
- 46.3
- Score
- 46.3
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:0
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 xHigh; launch table; third-party comparator rows are not copied
DeepSWE v1.1 (Show measurement, test conditions, and source)
- Source value
- 71
- Score
- 71
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:1
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 High; launch table; third-party comparator rows are not copied
EEBench (Show measurement, test conditions, and source)
- Source value
- 64
- Score
- 64
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:2
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 xHigh; launch table; third-party comparator rows are not copied
Terminal-Bench 4.0 (Show measurement, test conditions, and source)
- Source value
- 38
- Score
- 38
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:4
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 xHigh; launch table; third-party comparator rows are not copied
Harvey Legal Agent Benchmark (Show measurement, test conditions, and source)
- Source value
- 19.6
- Score
- 19.6
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:5
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 xHigh; launch table; third-party comparator rows are not copied
HealthBench Professional (Show measurement, test conditions, and source)
- Source value
- 56.7
- Score
- 56.7
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:6
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 xHigh; launch table; third-party comparator rows are not copied
AA Briefcase v1.1 (Show measurement, test conditions, and source)
- Source value
- 1657
- Score
- 1657
- Metric
- rating
- Unit
- rating
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:grok-4.7:3
- Source type
- vendor-reported
- Evaluator
- xAI
- Status
- active
- Retrieved at
- 2026-09-22
- Methodology
- Vendor-reported result. Grok 4.7 xHigh; launch table; third-party comparator rows are not copied
Our model tests
Our tests
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.
| Specification | Value and source |
|---|---|
| Weights | ProprietarySource |
| Access | APISource |
| Context window | 500,000 tokensSource |
| Notes | Model for coding, agentic tasks, and knowledge work with a 500,000-token context window. Supports text and image input and four reasoning levels. Parameter count not disclosed.Source |
| API model ID | grok-4.7Source |
| Source status | activeSource |
| Release | 2026-09-21Source |
| Maximum output | No separate output limitSource |
| Input | Text, ImageSource |
| Output | TextSource |
| Tool calling | YesSource |
| Structured output | YesSource |
| Reasoning mode | low, medium, high, xhigh (default: high)Source |
Pricing
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
Head-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
Show all comparisons (44)
More models
Models from the same selection
All AI models
Model generations
Predecessor and successor
Every relationship names its kind, its qualification and the dated source it rests on.
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Input | Documented modalities. Retrieved September 22, 2026. |
| Output | Documented modalities. Retrieved September 22, 2026. |
| Research status | Research date September 22, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | parameters-billions Original wording xAI does not publish Grok 4.7's parameter count in the model documentation. |
| Not published | active-parameters-billions Original wording xAI does not publish Grok 4.7's active parameter count in the model documentation. |
| Not published | knowledge-cutoff Original wording The official Grok 4.7 model page does not publish a knowledge cutoff date. |
| Additional source | xAI (retrieved September 22, 2026) |